AI Threat AlertAI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1527 results — Medium severityCVE-2026-55514vLLM: malformed prompt embeds crash serving via M-RoPE6.50.7%vllmJul 6MEDIECVE-2026-55438Coder: CORS bypass via workspace subdomain proxy5.80.2%github.com/coder/coder/v2Jul 6MEDICVE-2026-55437Coder: stored XSS in agent logs risks admin session5.40.3%github.com/coder/coder/v2Jul 6MEDICVE-2026-55435Coder AI Bridge: suspended user auth bypass5.40.3%github.com/coder/coder/v2Jul 6MEDICVE-2026-55434Coder: AI Bridge unbounded read enables DoS6.50.6%github.com/coder/coder/v2Jul 6MEDICVE-2026-55433Coder: missing ActionUpdate check allows devcontainer wipe5.40.4%github.com/coder/coder/v2Jul 6MEDICVE-2026-55432Coder: sub-agent apps bypass org port-sharing policy5.40.3%github.com/coder/coder/v2Jul 6MEDICVE-2026-55078Coder: zip decompression bomb crashes coderd (DoS)6.50.6%github.com/coder/coder/v2Jul 6MEDICVE-2026-55430Coder: X-Forwarded-Host spoof leaks victim app data5.80.2%github.com/coder/coder/v2Jul 6MEDICVE-2026-55079Coder: unbounded FileSize crashes coderd via OOM4.90.6%github.com/coder/coder/v2Jul 6MEDIECVE-2026-55646vLLM: audio upload OOMs process before size check6.50.5%vllmJul 6MEDICVE-2026-14898OpenAI Codex: prompt injection exfils data via images6.50.4%—Jul 6MEDICVE-2026-40257OP-TEE: off-by-one in SHA-3 CE overflows TEE kernel heap5.50.2%—Jul 6MEDICVE-2026-59152LangSmith SDK: arbitrary file read via TracingMiddleware5.00.2%langsmith-sdkJul 6MEDIECVE-2026-14647ONNX: OOB read in shape inference parsing untrusted models4.30.4%onnxJul 4MEDICVE-2026-9557Mautic Focus: SSRF enables internal network recon6.40.1%mautic/coreJul 2MEDIGHSA-4m3v-q747-pc6hOpenClaw: slash token revocation lag allows reuse——openclawJul 2MEDIGHSA-275c-xpvc-jgfwOpenClaw: Slack/Zalo webhook secrets outlive rotation——openclawJul 2MEDIGHSA-6c4r-g249-wv3cOpenClaw: sandbox leaks host workspace path to child——openclawJul 2MEDIGHSA-77pv-3w4q-vrj5OpenClaw: QQBot slash commands bypass allowFrom auth——openclawJul 2Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
Need deeper analysis?
Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.
Start 14-Day Free Trial